Comparison of speech-based in-car HMI concepts in a driving simulation study

Hansjörg Hofmann, Vanessa Tobisch, Ute Ehrlich, André Berton, Angela Mahr

In: Proceedings of the 19th International Conference on Intelligent User Interfaces. International Conference on Intelligent User Interfaces (IUI-14) Haifa Israel ACM 2014.


This paper reports experimental results from a driving simulation study in order to compare different speech-based in-car human-machine interface concepts. The effects of the use of a command-based and a conversational in-car speech dialog system on usability and driver distraction are evaluated. Different graphical user interface concepts have been designed in order to investigate their potential supportive or distracting effects. The results show that only few differences concerning speech dialog quality were found when comparing the speech dialog strategies. The command-based dialog was slightly better accepted than the conversational dialog, which can be attributed to the limited performance of the system’s language understanding component. No differences in driver distraction were revealed. Moreover, the study revealed that speech dialog systems without graphical user interface were accepted by participants in the driving environment and that the use of a graphical user interface impaired the driving performance and increased gaze-based distraction. In the driving scenario, the choice of speech dialog strategies does not have a strong influence on usability and no influence on driver distraction. Instead, when designing the graphical user interface of an in-car speech dialog systems, developers should consider reducing the content presented on the display device in order to reduce driver distraction.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence